Loading...
Loading...
Found 160 Skills
A qualitative research assistant tool based on Braun & Clarke's Reflexive Thematic Analysis framework. Supports two input modes: (1) Provide raw interview text directly → The skill completes initial TA coding for each document, then proceeds to theme identification after summarization; (2) Provide existing initial coding pool → Directly enter the process of clustering, review, and naming suggestions. Outputs a structured candidate theme table, clearly marking codes with ambiguous boundaries and naming suggestions to be decided by researchers. This skill is triggered when users mention terms such as "thematic analysis", "theme coding", "help me cluster codes", "extract themes from codes", "Braun Clarke", "candidate themes", "how to categorize these codes into themes", "help me check the theme structure", "conduct thematic analysis on interviews". Note the difference from grounded-coding: grounded-coding focuses on category construction and theoretical relationships for procedural grounded theory; thematic-analysis focuses on semantic theme identification following the Braun & Clarke approach, outputting theme structures rather than theoretical propositions.
Discover novel small molecule binders for protein targets using structure-based and ligand-based approaches. Creates actionable reports with candidate compounds, ADMET profiles, and synthesis feasibility. Use when users ask to find small molecules for a target, identify novel binders, perform virtual screening, or need hit-to-lead compound identification.
Track which stacks use a specific Pulumi package and at what versions, or upgrade a stack to the latest version of a package. Use when users ask about package version tracking, outdated package versions across stacks, upgrade candidates, or package usage audits. Also use when users want to upgrade/update a specific package version in a stack or project. Do NOT use for general infrastructure creation, resource provisioning, or questions about how to use a package.
Execute a complete tax-loss harvesting workflow from candidate identification through post-harvest monitoring. Use when the user asks about finding TLH candidates, gain/loss budgeting, replacement security selection, wash-sale compliance, or harvest execution planning. Also trigger when users mention 'unrealized losses in my portfolio', 'swap ETFs for tax purposes', 'harvest losses before year-end', 'substantially identical security', 'wash-sale window', 'NIIT offset', 'loss carryforward', or ask how much tax they can save by harvesting.
Design value propositions for candidate customer segments and help the user choose the strongest one. Use when Codex needs to explain jobs, pains, and gains when needed, check niche-positioning prerequisites, ask one question at a time, present multiple value-proposition options, and write user-confirmed outputs into `opc-doc/`.
Switch JDK, Kotlin, Gradle, Maven, or any SDKMAN-managed candidate when the user or runtime explicitly demands a different version. Use when the user says "switch to Java 17", "run with JDK 21", "use Gradle 8.x", asks about JAVA_HOME, a build fails with UnsupportedClassVersionError or "class file has wrong version", or the repo contains a `.sdkmanrc`. Operates on machines configured with SDKMAN (`$SDKMAN_DIR`, default `~/.sdkman`).
Find dead code and cleanup candidates such as unused exports, unreachable branches, orphaned files, stale feature flags, dead registrations, and compatibility layers with no live callers. Use when auditing refactors, bundle-size cleanup, architecture simplification, pre-release cleanup, reviewing requests to find unused code or decide what can be deleted, or when deciding whether code can be safely removed or auto-fixed.
Build and maintain one coherent company story across all audiences — employees, investors, customers, candidates, and partners. Detects narrative contradictions and ensures the same truth is framed for each audience's needs. Use when preparing investor updates, all-hands presentations, board communications, recruiting narratives, crisis communications, or when user mentions company narrative, messaging consistency, storytelling, all-hands, investor update, or crisis communication.
Meta-skill that forges, audits, and refines other skills. Three modes – forge a new skill from a brief, audit recent chat transcripts for new-skill candidates and pain points, or refine an existing skill with additive-only changes. Triggers on "skill-forge a thing that does X", "forge a skill", "skill-forge audit", "skill audit", "refine my skills", "skill-forge refine <name>", or "/skill-forge". Auto-opens a PR against mphinance/alpha-skills (never auto-merges).
Comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) profiling for drug candidates. Integrates ADMET-AI predictions, SwissADME drug-likeness, PubChemTox experimental toxicity, ChEMBL clinical data, Lipinski rule-of-five, and CYP interaction data. Use for drug-likeness assessment, BBB penetration, bioavailability, hepatotoxicity prediction, ADME/PK profiling, or screening compound libraries before lab testing.
Generate 10 brilliant ideas for powerful new functionality. Use when brainstorming features, improvements, or innovations for a system. Internally generates 100 candidates and filters to the top 10 most impactful, pragmatic, and innovative ideas.
Inspeccionar un proyecto existente para descubrir decisiones arquitectónicas implícitas y proponer ADRs candidatos. Usar cuando el usuario quiera auditar un repositorio en busca de decisiones no documentadas, pida "descubrir ADRs", "qué decisiones arquitectónicas tiene este proyecto", "busca ADRs en el repo", "analiza la arquitectura del proyecto" o cualquier variante que implique explorar el código/estructura para inferir decisiones relevantes que merezcan un ADR. Activar también cuando el usuario llegue a un proyecto nuevo y quiera entender qué decisiones ya se tomaron, aunque no mencione explícitamente "ADR".